Yuan Luo

我在Ubuntu 20.04上遇到类似的问题。 undefined reference to `google::FlagRegisterer::FlagRegisterer() https://github.com/apache/incubator-brpc/issues/1392

一个在外企工作15年的大头兵路过，看完你所有的技术和生活blog，你的经历也激励着我在技术道路上越走越深。祝福你一切顺利！

passed build client and server separately. but failed to build all.

我在Ubuntu 20.04上已经安装过rocksdb，比较新的版本。然后用pika submodule拉下来的rocksdb就编译不过。

> @Zeju1997 Hey, here is my solution to the puzzles: https://github.com/SiriusNEO/Triton-Puzzles-Lite/blob/main/puzzles_ans.py. Hoping this can help you! @SiriusNEO Thanks for the ans link to these puzzles. I'm wondering where we can...

有没有可能是 _kNumWrapGroups_ 和 _kNumWrapPerGroup_ 变量改反了？ 我们是H20上改成：kNumWarpsPerGroup = 8，kNumWarpGroups = 4 ``` sed -i 's/constexpr int kNumWarpsPerGroup = 10;/constexpr int kNumWarpsPerGroup = 8;/g' ./csrc/kernels/internode_ll.cu sed -i 's/constexpr int kNumWarpGroups = 3;/constexpr...

I encountered a similar issue in SGLang+DeepEP on one 8 x H20 node. Not sure it is related or not.  My command: ``` $NVSHMEM_DEBUG=INFO python3 -m sglang.compile_deep_gemm --model /root/DeepSeek-R1...

The intranode test finished successfully with no error. The internode test normal kernel has the same error. This error occurs 100%.

Env: 2 x 8 x H20. ``` root@0540de603a8e:/home/dpsk_a2a/DeepEP# nvidia-smi topo -m GPU0 GPU1 GPU2 GPU3 GPU4 GPU5 GPU6 GPU7 NIC0 NIC1 NIC2 NIC3 CPU Affinity NUMA Affinity GPU NUMA ID...

``` root@1e604ac9d157:/home/dpsk_a2a/DeepEP# /opt/nvshmem/bin/nvshmem-info -a NVSHMEM v3.2.5 Build Information: CUDA API 12080 CUDA Driver 12080 Build Timestamp May 13 2025 22:28:19 Build Variables NVSHMEM_DEBUG=OFF NVSHMEM_DEVEL=OFF NVSHMEM_DEFAULT_PMI2=OFF NVSHMEM_DEFAULT_PMIX=OFF NVSHMEM_DEFAULT_UCX=OFF NVSHMEM_ENABLE_ALL_DEVICE_INLINING=OFF NVSHMEM_GPU_COLL_USE_LDST=OFF NVSHMEM_IBGDA_SUPPORT=ON...